May 26, 2026
Cutting agent costs with pre-computed context
Pre-computing context as Knowledge Indicators reduces LLM agent token costs by up to 75% and improves answer accuracy from 60% to 92%. This post covers the extraction, retrieval and feedback loop that make it work, tested against the BrowseComp-Plus benchmark.
May 4, 2026
How to measure and improve Elasticsearch search recall: from 0.43 to 0.75 with hybrid search
Learn how to measure and improve search recall in Elasticsearch by combining BM25 lexical search with Jina AI vector embeddings, using the rank_eval API to validate the improvement with real numbers.
March 13, 2026
Entity resolution with Elasticsearch, part 4: The ultimate challenge
Solving and evaluating entity resolution challenges in a highly diverse “ultimate challenge” dataset designed to prevent shortcuts.
March 11, 2026
Hybrid search with Java: LangChain4j Elasticsearch integration
Learn how to use hybrid search in LangChain4j via its Elasticsearch integrations, with a complete Java example.
March 4, 2026
Entity resolution with Elasticsearch, part 3: Optimizing LLM integration with function calling
Learn how function calling enhances LLM integration, enabling a reliable and cost-efficient entity resolution pipeline in Elasticsearch.
February 26, 2026
Entity resolution with Elasticsearch & LLMs, Part 2: Matching entities with LLM judgment and semantic search
Using semantic search and transparent LLM judgment for entity resolution in Elasticsearch.
February 20, 2026
Ensuring semantic precision with minimum score
Improve semantic precision by employing minimum score thresholds. The article includes concrete examples for semantic and hybrid search.
February 12, 2026
Entity resolution with Elasticsearch & LLMs, Part 1: Preparing for intelligent entity matching
Learn what entity resolution is and how to prepare both sides of the entity resolution equation: your watch list and the articles you want to search.
February 11, 2026
From vectors to keywords: Elasticsearch hybrid search in LangChain
Learn how to use hybrid search in LangChain via its Elasticsearch integrations, with complete Python and JavaScript examples.